Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1987 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.9453. Min Range: -2.9453

Max Act: 2.9453. Min Act: -0.0000

Data Index: 603206 (C4 (Web Text))

Max Activating Token Index: 1013

Text #1

Max Range: 2.9453. Min Range: -2.9453

Max Act: 2.8364. Min Act: -0.0000

Data Index: 1350509 (C4 (Web Text))

Max Activating Token Index: 103

Text #2

Max Range: 2.9453. Min Range: -2.9453

Max Act: 2.6261. Min Act: -0.0000

Data Index: 258268 (C4 (Web Text))

Max Activating Token Index: 409

Text #3

Max Range: 2.9453. Min Range: -2.9453

Max Act: 2.4454. Min Act: -0.0000

Data Index: 859164 (C4 (Web Text))

Max Activating Token Index: 46

Text #4

Max Range: 2.9453. Min Range: -2.9453

Max Act: 2.5730. Min Act: -0.0000

Data Index: 941177 (C4 (Web Text))

Max Activating Token Index: 1019

Text #5

Max Range: 2.9453. Min Range: -2.9453

Max Act: 2.4064. Min Act: -0.0000

Data Index: 283036 (C4 (Web Text))

Max Activating Token Index: 1021

Text #6

Max Range: 2.9453. Min Range: -2.9453

Max Act: 2.5280. Min Act: -0.0000

Data Index: 8256 (C4 (Web Text))

Max Activating Token Index: 1001

Text #7

Max Range: 2.9453. Min Range: -2.9453

Max Act: 2.5020. Min Act: -0.0000

Data Index: 346561 (C4 (Web Text))

Max Activating Token Index: 45

Text #8

Max Range: 2.9453. Min Range: -2.9453

Max Act: 2.5114. Min Act: -0.0000

Data Index: 1304011 (C4 (Web Text))

Max Activating Token Index: 859

Text #9

Max Range: 2.9453. Min Range: -2.9453

Max Act: 2.4931. Min Act: -0.0000

Data Index: 906155 (C4 (Web Text))

Max Activating Token Index: 981

Text #10

Max Range: 2.9453. Min Range: -2.9453

Max Act: 2.4572. Min Act: -0.0000

Data Index: 877681 (C4 (Web Text))

Max Activating Token Index: 975

Text #11

Max Range: 2.9453. Min Range: -2.9453

Max Act: 2.4503. Min Act: -0.0000

Data Index: 275747 (C4 (Web Text))

Max Activating Token Index: 379

Text #12

Max Range: 2.9453. Min Range: -2.9453

Max Act: 2.4160. Min Act: -0.0000

Data Index: 1332330 (C4 (Web Text))

Max Activating Token Index: 380

Text #13

Max Range: 2.9453. Min Range: -2.9453

Max Act: 2.4178. Min Act: -0.0000

Data Index: 997426 (C4 (Web Text))

Max Activating Token Index: 567

Text #14

Max Range: 2.9453. Min Range: -2.9453

Max Act: 2.2937. Min Act: -0.0000

Data Index: 886492 (C4 (Web Text))

Max Activating Token Index: 975

Text #15

Max Range: 2.9453. Min Range: -2.9453

Max Act: 2.3650. Min Act: -0.0000

Data Index: 502809 (C4 (Web Text))

Max Activating Token Index: 213

Text #16

Max Range: 2.9453. Min Range: -2.9453

Max Act: 2.2507. Min Act: -0.0000

Data Index: 193648 (C4 (Web Text))

Max Activating Token Index: 997

Text #17

Max Range: 2.9453. Min Range: -2.9453

Max Act: 2.3700. Min Act: -0.0000

Data Index: 1234429 (C4 (Web Text))

Max Activating Token Index: 294

Text #18

Max Range: 2.9453. Min Range: -2.9453

Max Act: 2.2958. Min Act: -0.0000

Data Index: 1175384 (C4 (Web Text))

Max Activating Token Index: 120

Text #19

Max Range: 2.9453. Min Range: -2.9453

Max Act: 2.2879. Min Act: -0.0000

Data Index: 1263394 (C4 (Web Text))

Max Activating Token Index: 44